Curious what congress and Trump are saying about the coronavirus?

This analysis takes a look at the number, the positive and negative sentiment, and the content of the tweets, for each party and how that’s evolving over time since February 1, 2020.

I utilize open data hosted online. In particular, big thanks to Alex Litel who created the Tweets of Congress repo, where I pulled congressional tweets from, and the folks running Trump Twitter Archive, where I pulled Trump’s tweets from.

The repo for this project is: https://github.com/dcosme/congress-tweets-covid19

prep data

load packages

library(tidyverse)
library(jsonlite)
library(tidytext)
library(ggwordcloud)
library(knitr)
library(DT)
library(drlib)

define palettes

palette4 = wesanderson::wes_palette("Zissou1", 4, "continuous")
palette4 = c(palette4[1], palette4[2], palette4[4], palette4[3])
palette5 = wesanderson::wes_palette("Zissou1", 5, "continuous")
palette2 = c(palette5[2], palette5[4])

load congress twitter handles

congress_twitter = read.csv("~/Documents/code/US-Congress/116thCongress/116Congress.csv", stringsAsFactors = FALSE) %>%
  rename("name" = Wikipedia..Names) %>%
  gather(handle_type, twitter_handle, ODU.WSDL, CSPAN, TweetCongress, Github) %>%
  select(name, handle_type, twitter_handle) %>%
  mutate(twitter_handle = tolower(twitter_handle),
         twitter_handle = ifelse(twitter_handle == "", NA, twitter_handle),
         name = gsub("<e9>", "é", `Encoding<-`(name, "latin1"), fixed = TRUE),
         name = gsub("<e1>", "á", `Encoding<-`(name, "latin1"), fixed = TRUE),
         name = gsub("<fa>", "ú", `Encoding<-`(name, "latin1"), fixed = TRUE),
         name = gsub("<ed>", "í", `Encoding<-`(name, "latin1"), fixed = TRUE),
         name = gsub("é", "e", name),
         name = gsub("á", "a", name),
         name = gsub("ú", "u", name),
         name = gsub("í", "i", name),
         name = trimws(name)) %>%
  extract(name, c("first", "last"), "([A-Za-z]{1}).* (.*)", remove = FALSE) %>%
  spread(handle_type, twitter_handle)

congress = read.csv("~/Documents/code/us-senate/us-senate/data/us-senate.csv", stringsAsFactors = FALSE) %>%
  bind_rows(read.csv("~/Documents/code/us-house/us-house/data/us-house.csv", stringsAsFactors = FALSE)) %>%
  select(state_name, title, party, name, gender, ethnicity, twitter_handle) %>%
  mutate(twitter_handle = tolower(twitter_handle),
         twitter_handle = ifelse(twitter_handle == "", NA,
                          ifelse(twitter_handle == "housedemocrats", NA,
                          ifelse(twitter_handle == "senatorloeffler?lang=en", NA, twitter_handle))),
         name = gsub("é", "e", name),
         name = gsub("á", "a", name),
         name = gsub("ú", "u", name),
         name = gsub("í", "i", name),
         name = trimws(name)) %>%
  extract(name, c("first", "last"), "([A-Za-z]{1}).* (.*)", remove = FALSE)

congress_info = full_join(congress, congress_twitter, by = c("first", "last")) %>%
  gather(handle_type, twitter_handle, twitter_handle, ODU.WSDL, CSPAN, TweetCongress, Github) %>%
  select(state_name, title, party, first, last, gender, ethnicity, twitter_handle) %>%
  group_by(first, last) %>%
  fill(state_name, title, party, gender, ethnicity, twitter_handle, .direction = "updown") %>%
  unique() %>%
  filter(!is.na(state_name)) %>%
  ungroup() %>%
  mutate(last = tolower(last))

load congressional tweets

Tweets of Congress, updated daily
select tweets containing the following terms: corona|virus|covid|flu|social distancing|pandemic

pull to update repo

cd ~/Documents/code/congresstweets
git pull origin master

## From https://github.com/alexlitel/congresstweets
##  * branch            master     -> FETCH_HEAD
## Already up to date.

define keywords and words to ignore

keywords = "corona|virus|covid|flu|social distancing|pandemic"
ignore_root_words = "http|.com|img|jpg|video|live|index|[0-9]|corona|covid|vid|ncov|aspx|utm|t.co|png"
ignore_words = c("rt", "amp", "qt", "pu", "tag", "i'm", "it's", "i’m", "it’s", "lr", "li", "ag")

load the files

file_dir = "~/Documents/code/congresstweets/data"
file_pattern = "2020-0[2-3]{1}-.*.json"
file_list = list.files(file_dir, pattern = file_pattern)

tweets_temp = data.frame()

for (file in file_list) {
  temp = tryCatch(jsonlite::stream_in(file(file.path(file_dir, file)), verbose = FALSE), error = function(e) message(file))

  tweets_temp = rbind(tweets_temp, temp)
  rm(temp)
}

tweets_all = tweets_temp %>%
  rename("twitter_handle" = screen_name) %>%
  select(twitter_handle, time, text) %>%
  mutate(twitter_handle = tolower(twitter_handle),
         text = tolower(text)) %>%
  filter(grepl(keywords, text)) %>%
  rename("day" = time)

find missing congressional twitter handles

missing = tweets_all %>% 
  left_join(., congress_info) %>%
  filter(is.na(last)) %>%
  select(twitter_handle) %>%
  unique()

last_names = congress_info %>%
  ungroup() %>%
  select(last) %>%
  unique() %>%
  mutate(last = tolower(last))

missing$last <- sapply(missing$twitter_handle, function(handle) {
  last <- last_names$last[sapply(last_names$last, grepl, handle)]
  }) 

missing %>%
  unnest(last, keep_empty = TRUE) %>%
  mutate(first = toupper(substring(twitter_handle, 1, 1)),
         last = ifelse(is.na(last), "", last)) %>%
  write.csv(., "missing.csv", row.names = FALSE)

missing_edited = read.csv("missing_edited.csv", stringsAsFactors = FALSE)

congress_full = congress_info %>%
  full_join(., missing_edited, by = c("first", "last")) %>%
  gather(var, twitter_handle, contains("twitter_handle")) %>%
  select(-var) %>%
  unique() %>%
  filter(!is.na(twitter_handle)) %>%
  mutate(party = ifelse(party.y == "" | is.na(party.y), party.x, party.y)) %>%
  select(-c(party.x, party.y)) %>%
  unique() %>%
  filter(!is.na(party))

congress_tweets = tweets_all %>%
  left_join(., congress_full) %>%
  mutate(day = lubridate::as_date(day),
         week = lubridate::floor_date(day, "week"),
         month = lubridate::floor_date(day, "month"))

# congress_tweets %>%
#   filter(is.na(party)) %>%
#   select(twitter_handle) %>%
#   unique()

load trump tweets

get_tweets = function(year, fromJSON = TRUE) {
  ## build and send request
  url <- paste0(
    "http://trumptwitterarchive.com/",
    "data/realdonaldtrump/",
    year,
    ".json"
  )
  ## response object
  r <- httr::GET(url)
  ## check html status
  httr::warn_for_status(r)
  ## if fromJSON then convert to list otherwise return response object
  if (fromJSON) {
    r <- httr::content(r, "text")
    ## if html return empty data frame
    if (grepl("^\\<\\!DOCTYPE", r)) {
      r <- data.frame()
    } else {
      r <- jsonlite::fromJSON(r)
    }
  }
  r
}

trump_tweets = get_tweets(year = 2020) %>%
  mutate(twitter_handle = "realdonaldtrump",
         day = as.POSIXct(created_at, format = "%a %b %d %H:%M:%S %z %Y"),
         day = lubridate::as_date(day),
         week = lubridate::floor_date(day, "week"),
         month = lubridate::floor_date(day, "month"),
         party = "trump",
         first = "D",
         last = "trump",
         title = "president") %>%
  select(twitter_handle, text, day, week, month, party) %>%
  filter(grepl("2020-02|2020-03", month)) %>%
  mutate(text = tolower(text)) %>%
  filter(grepl(keywords, text))

merge tweets

tweets = bind_rows(congress_tweets, trump_tweets)

define wordcloud function

plot_number = function(data, timescale = "week", start_date = NULL, palette = palette4) {

  if (!is.null(start_date)) {
      data = data %>%
        filter(day >= start_date)
  }
  
  plot1 = data %>%
    filter(!is.na(party)) %>%
    ggplot(aes(!!sym(timescale), fill = party)) +
    geom_bar(stat = "count") +
    scale_fill_manual(name = "", values = palette) +
    labs(x = "", y = "number of tweets\n") +
    theme_minimal(base_size = 14) +
    theme(legend.position = "top")

  plot2 = data %>%
    filter(!is.na(party)) %>%
    ggplot(aes(!!sym(timescale), color = party)) +
    geom_line(stat = "count") +
    scale_color_manual(name = "", values = palette) +
    labs(x = "", y = "number of tweets\n") +
    theme_minimal(base_size = 14) +
    theme(legend.position = "top")
  
  return(list(plot1 = plot1, plot2 = plot2))
  
}

plot_sentiment = function(data, n_words = 20, 
                          start_date = NULL, duration = NULL, 
                          palette = palette2) {

  if (!is.null(start_date)) {
    if (!is.null(duration)) {
      data = data %>%
        filter(day >= start_date & day <= lubridate::date(start_date) + lubridate::days(duration))
    } else {
      data = data %>%
        filter(day >= start_date)
    }
  }
  
  sentiments = data %>%
    unnest_tokens(word, text) %>%
    inner_join(tidytext::get_sentiments("bing")) %>%
    anti_join(stop_words, by = "word") %>%
    filter(!grepl(ignore_root_words, word)) %>%
    filter(!word %in% ignore_words) %>%
    filter(!word == "trump") %>%
    group_by(party) %>%
    count(word, sentiment, sort = TRUE) %>%
    filter(party %in% c("democrat", "republican", "trump")) %>%
    top_n(n_words) %>%
    group_by(party) %>%
    arrange(n) %>%
    mutate(order = row_number())
  
  sentiments %>%
    ggplot(aes(drlib::reorder_within(word, n, party), n, fill = sentiment)) +
    geom_col() +
    drlib::scale_x_reordered() +
    facet_wrap(~party, scales = "free") +
    labs(y = "\nnumber of times tweeted",
         x = NULL) +
    coord_flip() +
    scale_fill_manual(name = "", values = palette) +
    theme_minimal(base_size = 14) +
    theme(legend.position = "top")
  
}

plot_content = function(data, party=NULL, start_date=NULL, duration=NULL, n_words=50, n_colors=6, size=20) {
  
  data = data %>%
      mutate(day = lubridate::as_date(day))
  
  if (!is.null(party)) {
    data = data %>%
      filter(party == !!party)
  }
  
  if (!is.null(start_date)) {
    if (!is.null(duration)) {
      data = data %>%
        filter(day >= start_date & day <= lubridate::date(start_date) + lubridate::days(duration))
    } else {
      data = data %>%
        filter(day >= start_date)
    }
  }
  
  palette = wesanderson::wes_palette("Zissou1", n_colors, "continuous")
  
  set.seed(42)
  
plot = data %>%
    filter(party %in% c("democrat", "republican", "trump")) %>%
    select(text, party) %>%
    unnest_tokens(word, text) %>%
    group_by(party) %>%
    count(word, sort = TRUE) %>%
    anti_join(stop_words, by = "word") %>%
    filter(!grepl(ignore_root_words, word)) %>%
    filter(!word %in% ignore_words) %>%
    slice(1:n_words) %>%
    mutate(word = gsub("[[:punct:]]", "", word),
           sum = sum(n),
           size = n / sum,
           tile = ntile(n, n_colors)) %>%
    ggplot(aes(label = word, size = size, color = as.factor(tile))) +
    geom_text_wordcloud_area(shape = "square", rm_outside = TRUE) +
      scale_size_area(max_size = size, trans = power_trans(1/.7)) +
      scale_color_manual(values = palette) +
      facet_wrap(~party) +
      theme_minimal() +
      theme(strip.text.x = element_text(size = 12))
  
  return(list(plot = plot, data = data))
}

number of tweets

How many times has Congress and the President tweeted about COVID-19?

daily

plot_number(tweets, timescale = "day")

## $plot1

## 
## $plot2

weekly

plot_number(tweets, timescale = "week")

## $plot1

## 
## $plot2

sentiment of tweets

How positive and negative is the content of the tweets?

Here is a list of the top 20 positive or negative words for each party and the President.

overall

plot_sentiment(tweets)

by month

February

plot_sentiment(tweets, start_date = "2020-02-01", duration = 28)

March

plot_sentiment(tweets, start_date = "2020-03-01", duration = 30)

by week

Here is a list of the top 10 positive or negative words for each party and the President by week.

Feb 1 - Feb 7

plot_sentiment(tweets, n_words = 10, start_date = "2020-02-01", duration = 6)

Feb 8 - Feb 14

plot_sentiment(tweets, n_words = 10, start_date = "2020-02-08", duration = 6)

Feb 15 - Feb 21

plot_sentiment(tweets, n_words = 10, start_date = "2020-02-15", duration = 6)

Feb 22 - Feb 28

plot_sentiment(tweets, n_words = 10, start_date = "2020-02-22", duration = 6)

Feb 29 - Mar 6

plot_sentiment(tweets, n_words = 10, start_date = "2020-02-29", duration = 6)

Mar 7 - Mar 13

plot_sentiment(tweets, n_words = 10, start_date = "2020-03-07", duration = 6)

Mar 14 - Mar 20

plot_sentiment(tweets, n_words = 10, start_date = "2020-03-14", duration = 6)

content of tweets

What are Congress and the President saying about COVID-19?

Here are 100 the most frequently used words by each party and the President.

overall

p = plot_content(tweets, start_date = "2020-02-01", n_words = 100)
p$plot

p$data %>%
  filter(party %in% c("democrat", "republican", "trump")) %>%
  group_by(party) %>%
  summarize(`number of tweets` = n()) %>%
  kable(format = "pandoc")

party	number of tweets
democrat	10836
republican	8598
trump	110

by month

February

p = plot_content(tweets, start_date = "2020-02-01", duration = 28, n_words = 100)
p$plot

p$data %>%
  filter(party %in% c("democrat", "republican", "trump")) %>%
  group_by(party) %>%
  summarize(`number of tweets` = n()) %>%
  kable(format = "pandoc")

party	number of tweets
democrat	1917
republican	1112
trump	24

March

p = plot_content(tweets, start_date = "2020-03-01", duration = 30, n_words = 100)
p$plot

p$data %>%
  filter(party %in% c("democrat", "republican", "trump")) %>%
  group_by(party) %>%
  summarize(`number of tweets` = n()) %>%
  kable(format = "pandoc")

party	number of tweets
democrat	8919
republican	7486
trump	86

by week

Here are 50 the most frequently used words by each party and the President for each week in February and March.

Feb 1 - Feb 7

p = plot_content(tweets, start_date = "2020-02-01", duration = 6)
p$plot

p$data %>%
  filter(party %in% c("democrat", "republican", "trump")) %>%
  group_by(party) %>%
  summarize(`number of tweets` = n()) %>%
  kable(format = "pandoc")

party	number of tweets
democrat	199
republican	133
trump	2

Feb 8 - Feb 14

p = plot_content(tweets, start_date = "2020-02-08", duration = 6)
p$plot

p$data %>%
  filter(party %in% c("democrat", "republican", "trump")) %>%
  group_by(party) %>%
  summarize(`number of tweets` = n()) %>%
  kable(format = "pandoc")

party	number of tweets
democrat	176
republican	162
trump	1

Feb 15 - Feb 21

p = plot_content(tweets, start_date = "2020-02-15", duration = 6)
p$plot

p$data %>%
  filter(party %in% c("democrat", "republican", "trump")) %>%
  group_by(party) %>%
  summarize(`number of tweets` = n()) %>%
  kable(format = "pandoc")

party	number of tweets
democrat	103
republican	80
trump	1

Feb 22 - Feb 28

p = plot_content(tweets, start_date = "2020-02-22", duration = 6)
p$plot

p$data %>%
  filter(party %in% c("democrat", "republican", "trump")) %>%
  group_by(party) %>%
  summarize(`number of tweets` = n()) %>%
  kable(format = "pandoc")

party	number of tweets
democrat	1222
republican	682
trump	19

Feb 29 - Mar 6

p = plot_content(tweets, start_date = "2020-02-29", duration = 6)
p$plot

p$data %>%
  filter(party %in% c("democrat", "republican", "trump")) %>%
  group_by(party) %>%
  summarize(`number of tweets` = n()) %>%
  kable(format = "pandoc")

party	number of tweets
democrat	2580
republican	2801
trump	24

Mar 7 - Mar 13

p = plot_content(tweets, start_date = "2020-03-07", duration = 6)
p$plot

p$data %>%
  filter(party %in% c("democrat", "republican", "trump")) %>%
  group_by(party) %>%
  summarize(`number of tweets` = n()) %>%
  kable(format = "pandoc")

party	number of tweets
democrat	5437
republican	4171
trump	55

Mar 14 - Mar 20

p = plot_content(tweets, start_date = "2020-03-14", duration = 6)
p$plot

p$data %>%
  filter(party %in% c("democrat", "republican", "trump")) %>%
  group_by(party) %>%
  summarize(`number of tweets` = n()) %>%
  kable(format = "pandoc")

party	number of tweets
democrat	1119
republican	569
trump	8

browse tweets

Who’s tweeting the most and what are they tweeting?

number of tweets

tweets %>%
  filter(!is.na(party)) %>%
  group_by(state_name, title, first, last, twitter_handle, party, gender, ethnicity) %>%
  summarize(n = n()) %>%
  arrange(desc(n)) %>%
  ungroup() %>%
  rename("state" = state_name,
         "twitter handle" = twitter_handle) %>%
  mutate(state = as.factor(state),
         title = as.factor(title),
         party = as.factor(party),
         gender = as.factor(gender),
         ethnicity = as.factor(ethnicity)) %>%
  DT::datatable(filter = "top", rownames = FALSE)

word counts

tweets %>%
  filter(!is.na(party)) %>%
  select(state_name, title, first, last, twitter_handle, party, gender, ethnicity, day, text) %>%
  arrange(twitter_handle) %>%
  unnest_tokens(word, text) %>%
  group_by(state_name, title, first, last, twitter_handle, party, gender, ethnicity) %>%
  count(word, sort = TRUE) %>%
  anti_join(stop_words, by = "word") %>%
  filter(!grepl(ignore_root_words, word)) %>%
  filter(!word %in% ignore_words) %>%
  ungroup() %>%
  rename("state" = state_name,
         "twitter handle" = twitter_handle) %>%
  mutate(state = as.factor(state),
         title = as.factor(title),
         party = as.factor(party),
         gender = as.factor(gender),
         ethnicity = as.factor(ethnicity)) %>%
  DT::datatable(filter = "top", rownames = FALSE)

tweets

tweets %>%
  select(state_name, title, first, last, twitter_handle, party, gender, ethnicity, day, text) %>%
  arrange(twitter_handle) %>%
  rename("state" = state_name,
         "twitter handle" = twitter_handle,
         "date" = day) %>%
  mutate(state = as.factor(state),
         title = as.factor(title),
         party = as.factor(party),
         gender = as.factor(gender),
         ethnicity = as.factor(ethnicity)) %>%
  DT::datatable(filter = "top", rownames = FALSE)

Congressional & Presidential Tweets About COVID-19

Dani Cosme

2020-03-15

prep data

number of tweets

daily

weekly

sentiment of tweets

overall

by month

February

March

by week

Feb 1 - Feb 7

Feb 8 - Feb 14

Feb 15 - Feb 21

Feb 22 - Feb 28

Feb 29 - Mar 6

Mar 7 - Mar 13

Mar 14 - Mar 20

content of tweets

overall

by month

February

March

by week

Feb 1 - Feb 7

Feb 8 - Feb 14

Feb 15 - Feb 21

Feb 22 - Feb 28

Feb 29 - Mar 6

Mar 7 - Mar 13

Mar 14 - Mar 20

browse tweets

number of tweets

word counts

tweets